People Data Labs

@peopledatalabs enrich the company data for Stripe — I need employee count, industry classification, and their main office location.

Based on People Data Labs records, Stripe is classified under Financial Services (SIC code 6099) with approximately 8,200 employees as of the last data refresh. Their headquarters is located at 510 Townsend Street, San Francisco, CA 94103. The enrichment also returns founding year (2010), estimated revenue band ($1B-$10B), and a list of 12 associated domain variations. Note that employee counts reflect PDL's aggregated data and may lag behind real-time hiring by several weeks.

This example shows the MCP's company enrichment capability, which requires at least one identifier (name, domain, or LinkedIn URL). The returned firmographics are aggregated from public sources and updated periodically — not live data. You'll need a valid API key with company enrichment quota remaining; rate limits apply at 600 requests/minute on standard plans.

@peopledatalabs clean this messy location string: 'sf bay area ca' — I need it standardized for our CRM import.

The location string has been cleaned and structured as: { "name": "San Francisco Bay Area", "locality": "San Francisco", "region": "California", "country": "United States", "continent": "North America", "geo": "37.7749,-122.4194" }. This standardized format resolves ambiguous abbreviations and provides consistent geographic hierarchy. The cleaning process matched the input against PDL's location database of 3+ million places worldwide.

Location cleaning is a read-only operation that standardizes unstructured address strings into structured JSON. It's useful for deduplicating CRM records or normalizing user-submitted location data. The tool works best with recognizable place names; highly ambiguous inputs (e.g., 'downtown') may return multiple candidates or fail to resolve. No side effects — this doesn't write anywhere.

@peopledatalabs I have a list of 40 partial email addresses from a lead form. Enrich each one with job title, company, and LinkedIn profile so we can prioritize outreach by seniority.

Enrichment completed for 34 of 40 email inputs (6 returned no match in PDL's database). The results include current job title, employer name, LinkedIn URL, and inferred seniority level for each matched record. For example, one lead at 'j.smith@techcorp.com' enriched to: Jane Smith, Senior Product Manager at TechCorp Inc., LinkedIn profile confirmed, seniority score 0.72 (director-level). The AI can now rank these leads by title keywords like 'VP', 'Director', 'Head of' to surface decision-makers first. Unmatched emails likely belong to individuals outside PDL's 3B+ person dataset or using personal addresses.

This synthesis example pairs the MCP's person enrichment tool with the AI's ability to batch-process and rank results. Person enrichment requires at least one identifier per record (email, phone, or name + company). Be aware: enriching contact data triggers privacy considerations — ensure compliance with GDPR, CCPA, and your own data policies. Each enrichment call consumes API credits; bulk operations can deplete quota quickly.

When People Data Labs beats manual LinkedIn scraping for SDR teams

A 3-person sales team at a B2B SaaS startup needs 200 qualified leads per week matching 'VP Engineering at Series A fintech companies in NYC'. The enrich-person and enrich-company tools let them validate email addresses and filter by employee count without touching LinkedIn's export limits. The clean-company tool standardizes messy CRM data so they stop emailing the wrong domain. This MCP is the right call if your ICP is narrow enough that you can describe it in 4-5 demographic filters and you need fresh contact data daily. If you're selling to SMBs where titles are inconsistent or your TAM is under 500 companies total, a static list from Apollo or ZoomInfo is cheaper. For teams running 10+ outbound campaigns simultaneously, the autocomplete and job-title-enrich tools speed up segmentation enough to justify the API cost.

How recruiting teams use this MCP to skip Boolean search hell

A 2-person recruiting team at a 40-person startup is hiring for a senior Rust engineer who's worked at a payments company. They use the enrich-person tool to pull GitHub profiles and past employers from a list of 80 inbound applicants, then the clean-school tool to verify degree claims without opening 80 browser tabs. The autocomplete tool helps them discover adjacent skills they didn't think to search for. This MCP wins when you're hiring for roles where LinkedIn's filters miss the signal—open-source contributors, bootcamp grads, people who changed careers. It's overkill if you're filling a generic PM role where LinkedIn Recruiter's native search already surfaces 300 qualified candidates. The break-even point is around 5 sourcing hours saved per week; below that, the API key setup and token spend aren't worth it.

When support teams enrich tickets with company context in real time

A 6-person support team at a developer-tools company gets 40 tickets daily from users at companies they've never heard of. They pipe the sender's email domain through the enrich-company tool to see employee count, funding stage, and industry before they reply. A 10-person startup gets a different response than a 2,000-person enterprise. The enrich-IP tool catches VPN users and flags tickets from competitors doing reconnaissance. This MCP is the right move if your product has a free tier or self-serve signup where you don't collect company size upfront, and your support SLA varies by account value. If you already gate signup behind a sales call or use Clearbit for enrichment, this is redundant. The threshold is whether you're triaging more than 20 cold inbound tickets per day—below that, manual LinkedIn lookups are faster than managing API quotas.